An online dynamic security assessment integrated scheme for power systems based on sparse multinomial naive bayes and canonical correlation forest

• Published in: Sustainable Energy, Grids and Networks Grids and Networks, 2024-09, Vol.39, p.101438, Article 101438
• Main Authors: Liu, Songkai, Li, Zhenghao, Li, Shichun, Li, Zhenxing, Miao, Shuwei, Zhang, Yating, Liu, Shuchi, Hu, Jingzhe, Ruan, Zhaohua, Xiao, Maoxiang, Sun, Jinming, Cui, Ziqi, Yang, Mingfei, Zhou, Qian, Zhao, Wenbo
• Format: Article
• Language: English
• Subjects: Canonical correlation forestMachine learning; Dynamic security assessment; Sparse multinomial naive Bayes; Transient stability margin
• ISSN: 2352-4677; 2352-4677
• DOI: 10.1016/j.segan.2024.101438

With the expansion of power systems and renewable energies, the security of power systems is confronted with severe situations. In this research, an online integrated DSA scheme based on sparse multinomial naive Bayes (SMNB) and canonical correlation forest (CCF) is proposed. The SMNB-based feature selection process selects the key features according to the correlations between the system operating variables and the DSA classification labels. Then, the DSA model is obtained by training CCFs with the key features. Finally, the results of DSA can be provided by the model on the basis of the real-time data of phasor measurement units (PMUs) in the wide area measurement system (WAMS). The online DSA integrated scheme is tested on the IEEE 39-bus system and a practical 1648-bus system provided by PSS/E software. The test results show that the proposed scheme is suitable for online application with providing satisfactory assessment accuracy. Furthermore, topology change, data noise and missing data are also taken into account for the robustness tests of the integrated scheme.